pathikrit

import shapeless._, syntax.singleton._, record._, ops.hlist._

/**
  * Given an instance A and it's generic representation AR and function f from AR => BR
  * we can covert A to B if we also have the generic representation of BR as B
  * We also handle misalignments using shapeless's align typeclass (https://stackoverflow.com/questions/29242873/shapeless-turn-a-case-class-into-another-with-fields-in-different-order)
  */
case class Morph[A, AR](a: A)(implicit reprA: LabelledGeneric.Aux[A, AR]) {
  // Why this DSL you say? Hack to get around scalac idiocy: https://stackoverflow.com/a/46614684/471136
  def to[B] = new {

pathikrit

import java.io.InputStream

import better.files._
import squants.information._, InformationConversions._

object GzipSplitter {
  /** Splits the $inputstream into approximately equal chunks of $splitSize gzip files under $outputDirectory */
  def split(
    inputStream      : InputStream,
    outputDirectory  : File         = File.newTemporaryDirectory(),

pathikrit

import java.nio.charset.{ Charset, StandardCharsets }

import org.apache.spark.sql._
import org.apache.spark.sql.types._

object SparkDataLoad {
  def fromCsv[A : Encoder](
    path:                     Set[String],
    encoding:                 Charset      = StandardCharsets.UTF_8,
    useHeader:                Boolean      = false,

pathikrit

 /** Distance between 2 coordinates (in degrees) */
  def dist(
    p1: (Double, Double),             // Coordinate 1 (in degrees)
    p2: (Double, Double),             // Coordinate 2 (in degrees)
    manhattanDist: Boolean = false,   // If true, calculate Manhattan distance on the sphere :)
    diameter: Double =  7917.5        // Diameter of Earth in miles; set this to whatever planet/units you want
  ): Double = {
    import Math._
    
    def haversine(theta: Double) = (1 - cos(theta))/2

pathikrit

import java.util.concurrent.TimeUnit

import scala.concurrent.duration.Duration

import com.google.common.util.concurrent.Monitor

class BooleanMonitor(monitor: Monitor = new Monitor())(check: => Boolean) {
  private val guard = new Monitor.Guard(monitor) { override def isSatisfied = check }

  def whenSatisfied[U](timeout: Duration = Duration.Inf)(f: => U): U = {

pathikrit

import org.apache.spark.sql.types._
import org.apache.spark.sql._

object SchemaDsl {
  case class ScalaToSparkType[ScalaType](sparkType: DataType, isNullable: Boolean = false) {
    def toField(name: String) = StructField(name     = name, dataType = sparkType, nullable = isNullable)
  }

  implicit val stringType: ScalaToSparkType[String] = ScalaToSparkType(StringType)
  implicit val intType: ScalaToSparkType[Int] = ScalaToSparkType(IntegerType)

pathikrit

import better.files._

def moveDupes(
  dir: File,
  logFile: File = (File.home / "dupes.txt"),
  dupeFolder: File = (File.home / 'dupes).createDirectory()
) = {
  for {
    log <- logFile.printWriter()
    (hash, toKeep :: toMove) <- dir.listRecursively.toSeq.groupBy(_.md5).mapValues(_.toList)

pathikrit

/**
  * Quick and dirty Scala app to print git commit punch-card e.g.
  *
  *    ┃08┃09┃10┃11┃12┃13┃14┃15┃16┃17┃18┃19┃20┃21┃22┃23┃00┃01┃02┃03┃04┃05┃06┃07┃
  * Sun┃▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
  * Mon┃▁▁▁▄▄▄▅▅▅▅▅▅▄▄▄▆▆▆▇▇▇▇▇▇███▆▆▆▅▅▅▄▄▄▃▃▃▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
  * Tue┃▁▁▁▃▃▃▆▆▆▅▅▅▅▅▅▅▅▅▆▆▆▇▇▇▆▆▆▆▆▆▅▅▅▅▅▅▄▄▄▃▃▃▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
  * Wed┃▁▁▁▄▄▄▅▅▅▇▇▇▅▅▅▅▅▅███▇▇▇▅▅▅▆▆▆▇▇▇▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
  * Thu┃▁▁▁▂▂▂▄▄▄▆▆▆▅▅▅▆▆▆▇▇▇▇▇▇▆▆▆▇▇▇▅▅▅▄▄▄▃▃▃▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
  * Fri┃▁▁▁▂▂▂▄▄▄▅▅▅▅▅▅▄▄▄▄▄▄▅▅▅▅▅▅▃▃▃▃▃▃▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁

pathikrit

triggeredMessage := Watched.clearWhenTriggered

libraryDependencies += "com.lihaoyi" % "ammonite" % "latest.release" % "test" cross CrossVersion.full

initialCommands in (Test, console) := """ammonite.Main().run()"""

watchSources ++= (
     (baseDirectory.value * "*.sbt").get
  ++ (baseDirectory.value / "project" * "*.scala").get
  ++ (baseDirectory.value / "project" * "*.sbt").get

pathikrit

import scala.collection.generic.Growable

/**
  * Boyer–Moore majority vote algorithm (https://en.wikipedia.org/wiki/Boyer–Moore_majority_vote_algorithm)
  * A Data structure that supports O(1) tracking of the majority element in streaming data
  * (i.e. something that occurs strictly > 50% of the time)
  */
class MajorityElement[A] extends Growable[A] {
  private[this] var majorityElement = Option.empty[A]
  private[this] var count = 0